© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58292
    Prev
    Next
    INDEX
    Explanations

    restaurants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     when
    -2.48
     there
    -2.45
     ensuring
    -2.20
     epitom
    -2.11
     giving
    -2.06
     because
    -2.06
     will
    -2.02
    ’
    -2.02
     making
    -2.02
     taking
    -2.00
    POSITIVE LOGITS
    
    2.45
     ridiculously
    2.30
     ludicrous
    2.20
     insanely
    2.14
     ส์
    2.11
     rése
    2.06
    嬸
    2.05
     !!!!
    2.00
     boister
    2.00
     trois
    1.99
    Activations Density 0.012%

    No Known Activations